no code implementations • 2 Jul 2023 • Tserendorj Adiya, Jae Shin Yoon, Jungeun Lee, Sanghun Kim, Hwasup Lim
To prove our claim, we design a novel human animation framework using a denoising diffusion model: a neural network learns to generate the image of a person by denoising temporal Gaussian noises whose intermediate results are cross-conditioned bidirectionally between consecutive frames.
no code implementations • 23 Jul 2021 • Sanghun Kim, Seungkyu Lee
However, sampling approaches which discard samples show limitations in some aspects such as the speed of training and optimality of the networks.
no code implementations • 1 Jan 2021 • Sanghun Kim, Seungkyu Lee
Generative Adversarial Networks (GANs) have achieved large attention and great success in various research areas, but it still suffers from training instability.